Infectious diseases kill millions of people annually worldwide. However, vaccination has proven to be an effective measure to control infectious diseases, and the rapid emergence of COVID-19 has shown the importance of developing safe and effective vaccines in a minimal time frame.
Published in Scientific Reports, researchers at Baylor College of Medicine and Amity University in Noida, India, have discovered a way to speed up vaccine development using artificial intelligence. They have developed an artificial intelligence platform to find important vaccine targets and epitopes that could transform the vaccine discovery process for deadly infectious diseases such as COVID-19 and Chagas disease. The platform was successfully tested on 40 different pathogens, which includes deadly SARS-CoV-2 (COVID-19), Mycobacterium tuberculosis (TB), Vibro cholerae (cholera) and Plasmodium falciparum (malaria).
The team of researchers tested the platform on several experimentally known vaccine targets, including vaccines in the market. They have a long-standing interest in neglected diseases of poverty, so they opted to analyze the whole genome and proteome (set of all protein sequences in a cell) of an important pathogen known as trypanosoma cruzi (T. cruzi).
“First, we shortlisted eight important proteins from the set of 19,000 proteins and then identified top epitopes (the part of an antigen molecule to which an antibody attaches itself) from these targets,” said Dr. Peter Hotez, dean of the National School of Tropical Medicine at Baylor. “Subsequently, we designed a multi-epitope vaccine against Chagas disease. This was followed by sophisticated analysis using bioinformatics tools to find whether the proposed vaccine is able to activate the immune system.”
Approximately 6 to 7 million people worldwide, mostly in Latin America, are estimated to be infected with T. cruzi, the parasite that causes Chagas disease. According to the World Health Organization, Chagas disease patients are at risk to suffer from severe illness from COVID-19.
“An ideal vaccine target should not be similar to host proteins (humans) in order to avoid cross reaction and subsequent side effects, therefore special care was taken to filter such data during the study,” said Dr. Maria Elena Bottazzi, associate dean of the National School of Tropical Medicine at Baylor.
The next line of action is to inject mice with these vaccines to demonstrate that the designed vaccines are nontoxic and produce enough antibodies before entering into clinical trials. “Right now, it is too early to tell how this work will affect patients down the line, but initial data suggest that the platform will be beneficial in several ways,” said Dr. Ulrich Strych, associate professor of pediatrics – tropical medicine at Baylor.
In wake of the Delta variant, the team also is engaging with various pharmaceutical and biotechnology companies to develop new vaccines against emerging infectious diseases.
“Proposing new vaccine targets (antigens) using computers that would work in the laboratory as well as in clinics is a challenging problem,” said Dr. Kamal Rawal, associate professor and project director of Amity University and the lead author of the study. “The key innovation is using artificial intelligence to combine several hundred parameters to mine several thousand proteins and genes to reach to the right targets and design vaccine using these proteins.”
The research was supported by the Kleberg Foundation and Baylor College of Medicine.